Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0780)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 780 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9456 |
| Val Accuracy | 0.8829 |
| Test Accuracy | 0.8784 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, tractor, television, dinosaur, possum, clock, lamp, wolf, seal, sweet_pepper, turtle, streetcar, willow_tree, worm, baby, skyscraper, snail, elephant, spider, table, sea, trout, cockroach, rose, plate, cattle, lizard, aquarium_fish, forest, mouse, lion, boy, bottle, chair, tulip, cloud, flatfish, kangaroo, motorcycle, raccoon, man, cup, telephone, orange, sunflower, snake, beaver, orchid, shark, bowl
- Downloads last month
- 7
Model tree for ProbeX/Model-J__ResNet__model_idx_0780
Base model
microsoft/resnet-101